NFS: teach nfs_neg_need_reval to understand LOOKUP_RCU

This requires nfs_check_verifier to take an rcu_walk flag, and requires
an rcu version of nfs_revalidate_inode which returns -ECHILD rather
than making an RPC call.

With this, nfs_lookup_revalidate can call nfs_neg_need_reval in
RCU-walk mode.

We can also move the LOOKUP_RCU check past the nfs_check_verifier()
call in nfs_lookup_revalidate.

If RCU_WALK prevents nfs_check_verifier or nfs_neg_need_reval from
doing a full check, they return a status indicating that a revalidation
is required.  As this revalidation will not be possible in RCU_WALK
mode, -ECHILD will ultimately be returned, which is the desired result.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>

2 files changed, 51 insertions, 17 deletions

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 8a3c36984fc4..dcd4fe5831d6 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -988,9 +988,13 @@ EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate);
  * A check for whether or not the parent directory has changed.
  * In the case it has, we assume that the dentries are untrustworthy
  * and may need to be looked up again.
+ * If rcu_walk prevents us from performing a full check, return 0.
  */
-static int nfs_check_verifier(struct inode *dir, struct dentry *dentry)
+static int nfs_check_verifier(struct inode *dir, struct dentry *dentry,
+                              int rcu_walk)
 {
+        int ret;
+
         if (IS_ROOT(dentry))
                 return 1;
         if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
@@ -998,7 +1002,11 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry)
         if (!nfs_verify_change_attribute(dir, dentry->d_time))
                 return 0;
         /* Revalidate nfsi->cache_change_attribute before we declare a match */
-        if (nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0)
+        if (rcu_walk)
+                ret = nfs_revalidate_inode_rcu(NFS_SERVER(dir), dir);
+        else
+                ret = nfs_revalidate_inode(NFS_SERVER(dir), dir);
+        if (ret < 0)
                 return 0;
         if (!nfs_verify_change_attribute(dir, dentry->d_time))
                 return 0;
@@ -1054,6 +1062,9 @@ out_force:
  *
  * If parent mtime has changed, we revalidate, else we wait for a
  * period corresponding to the parent's attribute cache timeout value.
+ *
+ * If LOOKUP_RCU prevents us from performing a full check, return 1
+ * suggesting a reval is needed.
  */
 static inline
 int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
@@ -1064,7 +1075,7 @@ int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
                 return 0;
         if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG)
                 return 1;
-        return !nfs_check_verifier(dir, dentry);
+        return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU);
 }
 
 /*
@@ -1101,11 +1112,11 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
         inode = dentry->d_inode;
 
         if (!inode) {
-                if (flags & LOOKUP_RCU)
-                        return -ECHILD;
-
-                if (nfs_neg_need_reval(dir, dentry, flags))
+                if (nfs_neg_need_reval(dir, dentry, flags)) {
+                        if (flags & LOOKUP_RCU)
+                                return -ECHILD;
                         goto out_bad;
+                }
                 goto out_valid_noent;
         }
 
@@ -1120,16 +1131,21 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
         if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ))
                 goto out_set_verifier;
 
-        if (flags & LOOKUP_RCU)
-                return -ECHILD;
-
         /* Force a full look up iff the parent directory has changed */
-        if (!nfs_is_exclusive_create(dir, flags) && nfs_check_verifier(dir, dentry)) {
+        if (!nfs_is_exclusive_create(dir, flags) &&
+            nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) {
+
+                if (flags & LOOKUP_RCU)
+                        return -ECHILD;
+
                 if (nfs_lookup_verify_inode(inode, flags))
                         goto out_zap_parent;
                 goto out_valid;
         }
 
+        if (flags & LOOKUP_RCU)
+                return -ECHILD;
+
         if (NFS_STALE(inode))
                 goto out_bad;
 
@@ -1566,14 +1582,23 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
                 struct dentry *parent;
                 struct inode *dir;
 
-                if (flags & LOOKUP_RCU)
-                        return -ECHILD;
-
-                parent = dget_parent(dentry);
-                dir = parent->d_inode;
+                if (flags & LOOKUP_RCU) {
+                        parent = rcu_dereference(dentry);
+                        dir = ACCESS_ONCE(parent->d_inode);
+                        if (!dir)
+                                return -ECHILD;
+                } else {
+                        parent = dget_parent(dentry);
+                        dir = parent->d_inode;
+                }
                 if (!nfs_neg_need_reval(dir, dentry, flags))
                         ret = 1;
-                dput(parent);
+                else if (flags & LOOKUP_RCU)
+                        ret = -ECHILD;
+                if (!(flags & LOOKUP_RCU))
+                        dput(parent);
+                else if (parent != rcu_dereference(dentry))
+                        return -ECHILD;
                 goto out;
         }
 
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 9927913c97c2..147fd17e7920 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1002,6 +1002,15 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 }
 EXPORT_SYMBOL_GPL(nfs_revalidate_inode);
 
+int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode)
+{
+        if (!(NFS_I(inode)->cache_validity &
+                        (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_LABEL))
+                        && !nfs_attribute_cache_expired(inode))
+                return NFS_STALE(inode) ? -ESTALE : 0;
+        return -ECHILD;
+}
+
 static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping)
 {
         struct nfs_inode *nfsi = NFS_I(inode);